Outpatient reception via collaboration between nurses and a large language model: a randomized controlled trial

Wan, Peixing1,2; Huang, Zigeng1; Tang, Wenjun1; Nie, Yulan3; Pei, Dajun4; Deng, Shaofen3; Chen, Jing4; Zhou, Yizhi3; Duan, Hongru3; Chen, Qingyu5; Long, Erping1

2024-07-01

10.1038/s41591-024-03148-7

NATURE MEDICINE   影响因子和分区

1078-8956

1546-170X

Reception is an essential process for patients seeking medical care and a critical component influencing the healthcare experience. However, current communication systems rely mainly on human efforts, which are both labor and knowledge intensive. A promising alternative is to leverage the capabilities of large language models (LLMs) to assist the communication in medical center reception sites. Here we curated a unique dataset comprising 35,418 cases of real-world conversation audio corpus between outpatients and receptionist nurses from 10 reception sites across two medical centers, to develop a site-specific prompt engineering chatbot (SSPEC). The SSPEC efficiently resolved patient queries, with a higher proportion of queries addressed in fewer rounds of queries and responses (Q & Rs; 68.0% <= 2 rounds) compared with nurse-led sessions (50.5% <= 2 rounds) (P = 0.009) across administrative, triaging and primary care concerns. We then established a nurse-SSPEC collaboration model, overseeing the uncertainties encountered during the real-world deployment. In a single-center randomized controlled trial involving 2,164 participants, the primary endpoint indicated that the nurse-SSPEC collaboration model received higher satisfaction feedback from patients (3.91 +/- 0.90 versus 3.39 +/- 1.15 in the nurse group, P < 0.001). Key secondary outcomes indicated reduced rate of repeated Q&R (3.2% versus 14.4% in the nurse group, P < 0.001) and reduced negative emotions during visits (2.4% versus 7.8% in the nurse group, P < 0.001) and enhanced response quality in terms of integrity (4.37 +/- 0.95 versus 3.42 +/- 1.22 in the nurse group, P < 0.001), empathy (4.14 +/- 0.98 versus 3.27 +/- 1.22 in the nurse group, P < 0.001) and readability (3.86 +/- 0.95 versus 3.71 +/- 1.07 in the nurse group, P = 0.006). Overall, our study supports the feasibility of integrating LLMs into the daily hospital workflow and introduces a paradigm for improving communication that benefits both patients and nurses.

SCI

英语

其他

National Natural Science Foundation of China (Excellent Youth Scholars Program)["32300483","82090011"] ; Chinese Academy of Medical Sciences Innovation Fund[2023-I2M-3-010]

Biochemistry & Molecular Biology ; Cell Biology ; Research & Experimental Medicine

Biochemistry & Molecular Biology ; Cell Biology ; Medicine, Research & Experimental

WOS:001267740800004

NATURE PORTFOLIO

MOLECULAR BIOLOGY & GENETICS

Web of Science

1.Chinese Acad Med Sci & Peking Union Med Coll, Inst Basic Med Sci, State Key Lab Resp Hlth & Multimorbid, Beijing, Peoples R China
2.NCI, Lab Immune Cell Biol, Ctr Canc Res, NIH, Bethesda, MD USA
3.Southern Univ Sci & Technol, Yantian Hosp, Shenzhen, Peoples R China
4.Wuhan Univ, Renmin Hosp, Wuhan, Peoples R China
5.Yale Univ, Sch Med, Sect Biomed Informat & Data Sci, New Haven, CT 06520 USA

Wan, Peixing,Huang, Zigeng,Tang, Wenjun,et al. Outpatient reception via collaboration between nurses and a large language model: a randomized controlled trial[J]. NATURE MEDICINE,2024.

Wan, Peixing.,Huang, Zigeng.,Tang, Wenjun.,Nie, Yulan.,Pei, Dajun.,...&Long, Erping.(2024).Outpatient reception via collaboration between nurses and a large language model: a randomized controlled trial.NATURE MEDICINE.

Wan, Peixing,et al."Outpatient reception via collaboration between nurses and a large language model: a randomized controlled trial".NATURE MEDICINE (2024).